© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 6253
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ill" or phrases related to illness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.72
    Források
    -0.63
    verwijspagina
    -0.61
     AssemblyCulture
    -0.61
    حوالہ
    -0.58
    JvmStatic
    -0.58
     Waray
    -0.58
    rungsseite
    -0.56
    AppCompatTheme
    -0.56
     StatelessWidget
    -0.55
    POSITIVE LOGITS
     ill
    1.06
     Ill
    0.75
     poorly
    0.69
    Ill
    0.69
     microphone
    0.69
     Holy
    0.63
    ArrowToggle
    0.63
     unwell
    0.62
    الإنجليزية
    0.61
     drafting
    0.60
    Activations Density 0.120%

    No Known Activations